Update app.py

app.py

@@ -26,54 +26,111 @@ CONTEXT_SIZES = {
 }
 
 MODEL_CONTEXT_SIZES = {
-   "Clipboard only": 4096,
-   "OpenAI ChatGPT": {
-       "gpt-3.5-turbo": 4096,
-       "gpt-4": 8192, 
-       "gpt-4-32k": 32768
-   },
-   "HuggingFace Inference": {
-       "microsoft/phi-3-mini-4k-instruct": 4096,
-       "HuggingFaceH4/zephyr-7b-beta": 8192,
-       "deepseek-ai/DeepSeek-Coder-V2-Instruct": 8192,
-       "meta-llama/Llama-3-8b-Instruct": 8192,
-       "mistralai/Mistral-7B-Instruct-v0.3": 32768,
-       "NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO": 32768
-   },
-   "Groq API": {
-       "gemma-7b-it": 8192,
-       "llama-3.1-70b": 32768,
-       "mixtral-8x7b-32768": 32768,
-       "llama-3.1-8b": 8192
-   }
+    "Clipboard only": 4096,
+    "OpenAI ChatGPT": {
+        "gpt-3.5-turbo": 16385,
+        "gpt-3.5-turbo-0125": 16385,
+        "gpt-3.5-turbo-1106": 16385,
+        "gpt-3.5-turbo-instruct": 4096,
+        "gpt-4": 8192,
+        "gpt-4-0314": 8192,
+        "gpt-4-0613": 8192,
+        "gpt-4-turbo": 128000,
+        "gpt-4-turbo-2024-04-09": 128000,
+        "gpt-4-turbo-preview": 128000,
+        "gpt-4-0125-preview": 128000,
+        "gpt-4-1106-preview": 128000,
+        "gpt-4o": 128000,
+        "gpt-4o-2024-11-20": 128000,
+        "gpt-4o-2024-08-06": 128000,
+        "gpt-4o-2024-05-13": 128000,
+        "chatgpt-4o-latest": 128000,
+        "gpt-4o-mini": 128000,
+        "gpt-4o-mini-2024-07-18": 128000,
+        "gpt-4o-realtime-preview": 128000,
+        "gpt-4o-realtime-preview-2024-10-01": 128000,
+        "gpt-4o-audio-preview": 128000,
+        "gpt-4o-audio-preview-2024-10-01": 128000,
+        "o1-preview": 128000,
+        "o1-preview-2024-09-12": 128000,
+        "o1-mini": 128000,
+        "o1-mini-2024-09-12": 128000,
+    },
+    "HuggingFace Inference": {
+        "microsoft/phi-3-mini-4k-instruct": 4096,
+        "microsoft/Phi-3-mini-128k-instruct": 131072, # Added Phi-3 128k
+        "HuggingFaceH4/zephyr-7b-beta": 8192,
+        "deepseek-ai/DeepSeek-Coder-V2-Instruct": 8192,
+        "meta-llama/Llama-3-8b-Instruct": 8192,
+        "mistralai/Mistral-7B-Instruct-v0.3": 32768,
+        "NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO": 32768,
+        "microsoft/Phi-3.5-mini-instruct": 4096,
+        "HuggingFaceTB/SmolLM2-1.7B-Instruct": 2048,
+        "google/gemma-2-2b-it": 2048,
+        "openai-community/gpt2": 1024,
+        "microsoft/phi-2": 2048,
+        "TinyLlama/TinyLlama-1.1B-Chat-v1.0": 2048
+    },
+    "Groq API": {
+        "gemma2-9b-it": 8192,
+        "gemma-7b-it": 8192,
+        "llama-3.3-70b-versatile": 131072,
+        "llama-3.1-70b-versatile": 131072, # Deprecated
+        "llama-3.1-8b-instant": 131072,
+        "llama-guard-3-8b": 8192,
+        "llama3-70b-8192": 8192,
+        "llama3-8b-8192": 8192,
+        "mixtral-8x7b-32768": 32768,
+        "llama3-groq-70b-8192-tool-use-preview": 8192,
+        "llama3-groq-8b-8192-tool-use-preview": 8192,
+        "llama-3.3-70b-specdec": 131072,
+        "llama-3.1-70b-specdec": 131072,
+        "llama-3.2-1b-preview": 131072,
+        "llama-3.2-3b-preview": 131072,
+    }
 }
 
 class ModelRegistry:
    def __init__(self):
        # HuggingFace Models
        self.hf_models = {
-           "Phi-3 Mini 4K": "microsoft/phi-3-mini-4k-instruct",
-           "Phi-3 Mini 128k": "microsoft/Phi-3-mini-128k-instruct", 
-           "Zephyr 7B Beta": "HuggingFaceH4/zephyr-7b-beta",
-           "DeepSeek Coder V2": "deepseek-ai/DeepSeek-Coder-V2-Instruct",
-           "Meta Llama 3.1 8B": "meta-llama/Llama-3-8b-Instruct",
-           "Meta Llama 3.1 70B": "meta-llama/Meta-Llama-3.1-70B-Instruct",
-           "Mixtral 7B": "mistralai/Mistral-7B-Instruct-v0.3", 
-           "Nous-Hermes": "NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO",
-           "Cohere Command R+": "CohereForAI/c4ai-command-r-plus",
-           "Aya 23-35B": "CohereForAI/aya-23-35B",
-           "Custom Model": ""
-       }
+            "Phi-3 Mini 4K": "microsoft/phi-3-mini-4k-instruct",
+            "Phi-3 Mini 128k": "microsoft/Phi-3-mini-128k-instruct", # Added
+            "Zephyr 7B Beta": "HuggingFaceH4/zephyr-7b-beta",
+            "DeepSeek Coder V2": "deepseek-ai/DeepSeek-Coder-V2-Instruct",
+            "Meta Llama 3.1 8B": "meta-llama/Llama-3-8b-Instruct",
+            "Meta Llama 3.1 70B": "meta-llama/Meta-Llama-3.1-70B-Instruct",
+            "Mixtral 7B": "mistralai/Mistral-7B-Instruct-v0.3",
+            "Nous-Hermes": "NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO",
+            "Cohere Command R+": "CohereForAI/c4ai-command-r-plus",
+            "Aya 23-35B": "CohereForAI/aya-23-35B",
+            "Phi-3.5 Mini": "microsoft/Phi-3.5-mini-instruct", # Added
+            "SmolLM2 1.7B": "HuggingFaceTB/SmolLM2-1.7B-Instruct", # Added
+            "Gemma 2 2B": "google/gemma-2-2b-it", # Added
+            "GPT2": "openai-community/gpt2", # Added
+            "Phi-2": "microsoft/phi-2", # Added
+            "TinyLlama 1.1B": "TinyLlama/TinyLlama-1.1B-Chat-v1.0", # Added
+            "Custom Model": ""  # Keep for custom models
+        }
        
        # Default Groq Models
-       self.default_groq_models = {
-           "gemma-7b-it": "gemma-7b-it",
-           "llama-3.1-70b-8192": "llama-3.1-70b-8192",
-           "llama-3.1-70b-versatile": "llama-3.1-70b-versatile",
-           "mixtral-8x7b-32768": "mixtral-8x7b-32768",
-           "llama-3.1-8b-instant": "llama-3.1-8b-instant",
-           "llama-3.1-70b-8192-tool-use-preview": "llama3-groq-70b-8192-tool-use-preview"
-       }
+       self.default_groq_models = {  # Keep defaults in case fetching fails
+            "gemma2-9b-it": "gemma2-9b-it",
+            "gemma-7b-it": "gemma-7b-it",
+            "llama-3.3-70b-versatile": "llama-3.3-70b-versatile",
+            "llama-3.1-70b-versatile": "llama-3.1-70b-versatile", # Deprecated
+            "llama-3.1-8b-instant": "llama-3.1-8b-instant",
+            "llama-guard-3-8b": "llama-guard-3-8b",
+            "llama3-70b-8192": "llama3-70b-8192",
+            "llama3-8b-8192": "llama3-8b-8192",
+            "mixtral-8x7b-32768": "mixtral-8x7b-32768",
+            "llama3-groq-70b-8192-tool-use-preview": "llama3-groq-70b-8192-tool-use-preview",
+            "llama3-groq-8b-8192-tool-use-preview": "llama3-groq-8b-8192-tool-use-preview",
+            "llama-3.3-70b-specdec": "llama-3.3-70b-specdec",
+            "llama-3.1-70b-specdec": "llama-3.1-70b-specdec",
+            "llama-3.2-1b-preview": "llama-3.2-1b-preview",
+            "llama-3.2-3b-preview": "llama-3.2-3b-preview",
+        }
        
        self.groq_models = self._fetch_groq_models()
 
@@ -341,12 +398,15 @@ def send_to_groq(prompt: str, model_name: str, api_key: str) -> str:
         return f"Error with Groq API: {str(e)}"
 
 def send_to_openai(prompt: str, api_key: str, model: str = "gpt-3.5-turbo") -> str:
-    """Send prompt to OpenAI API with better error handling."""
+    """Send prompt to OpenAI API using the new v1.0+ client format."""
     try:
-        import openai
-        openai.api_key = api_key
+        from openai import OpenAI  # Import the new client
         
-        response = openai.ChatCompletion.create(
+        # Initialize the client with the API key
+        client = OpenAI(api_key=api_key)
+        
+        # Create chat completion using new format
+        response = client.chat.completions.create(
             model=model,
             messages=[
                 {"role": "system", "content": "You are a helpful assistant that provides detailed responses."},
@@ -356,7 +416,15 @@ def send_to_openai(prompt: str, api_key: str, model: str = "gpt-3.5-turbo") -> s
             max_tokens=500,
             top_p=0.95
         )
-        return response.choices[0].message.content
+        
+        # Extract the response content
+        if response.choices and len(response.choices) > 0:
+            return response.choices[0].message.content
+        else:
+            return "Error: No response generated"
+            
+    except ImportError:
+        return "Error: Please install the latest version of openai package (pip install --upgrade openai)"
     except Exception as e:
         logging.error(f"OpenAI API error: {e}")
         return f"Error with OpenAI API: {str(e)}"